Dim the Lights! -- Low-Rank Prior Temporal Data for Specular-Free Video Recovery
This addresses the challenge of recovering specular-free videos for computer vision applications, particularly in scenarios with complex motions, but it is incremental as it builds on prior work in detection and inpainting.
The paper tackles the problem of specular reflections in videos, which cause information loss and discontinuity, by proposing a two-step framework for detection and restoration that uses low-rank prior temporal data to exploit spatio-temporal correlations. The result is improved detection accuracy and inpainting quality compared to existing approaches, with potential applications to other problems like object removal.
The appearance of an object is significantly affected by the illumination conditions in the environment. This is more evident with strong reflective objects as they suffer from more dominant specular reflections, causing information loss and discontinuity in the image domain. In this paper, we present a novel framework for specular-free video recovery with special emphasis on dealing with complex motions coming from objects or camera. Our solution is a twostep approach that allows for both detection and restoration of the damaged regions on video data. We first propose a spatially adaptive detection term that searches for the damage areas. We then introduce a variational solution for specular-free video recovery that allows exploiting spatio-temporal correlations by representing prior data in a low-rank form. We demonstrate that our solution prevents major drawbacks of existing approaches while improving the performance in both detection accuracy and inpainting quality. Finally, we show that our approach can be applied to other problems such as object removal.